This publicly available benchmark dataset is itended for testing and evaluating of garment segmentation, recognition and folding algorithms. The dataset is free for research and educational purposes and can be used in scientific publications at the condition of respecting the requested citation acknowledgment.
The documentation can be found in the attached research report.
The dataset is splitted into two roughly 2 GB packages that can be downloaded separatedly.
sample.zip small sample of flat wrinkled and folded samples.
00001-02050.zip contains flat and wrinkled samples.
02051-03442.zip contains folded samples.
In addition to the dataset we also provide a repository of simple Matlab tools to get started. This repository is also used as a bugtracker.
All publications making use of the CTU Garment Sorting Dataset must include the following citation (bibtex):
Wagner, L., Krejčová, D., and Smutný, V. CTU color and depth image dataset of spread garments. Research Report CTU–CMP–2013–25, Center for Machine Perception, K13133 FEE Czech Technical University, Prague, Czech Republic, September 2013.
Maintained by Libor Wagner, last update on